SUTrack: Towards Simple and Unified Single Object Tracking

TL;DR

SUTrack introduces a unified single object tracking framework capable of handling five diverse SOT tasks with a single model, reducing redundancy and enhancing cross-modal knowledge sharing, while outperforming task-specific models across multiple datasets.

Contribution

The paper presents a novel unified SOT framework that consolidates multiple tracking tasks into one model trained in a single session, with auxiliary strategies to boost performance.

Findings

Outperforms previous task-specific models on 11 datasets.

Effectively handles five diverse SOT tasks with a single model.

Provides models suitable for both edge devices and high-performance GPUs.

Abstract

In this paper, we propose a simple yet unified single object tracking (SOT) framework, dubbed SUTrack. It consolidates five SOT tasks (RGB-based, RGB-Depth, RGB-Thermal, RGB-Event, RGB-Language Tracking) into a unified model trained in a single session. Due to the distinct nature of the data, current methods typically design individual architectures and train separate models for each task. This fragmentation results in redundant training processes, repetitive technological innovations, and limited cross-modal knowledge sharing. In contrast, SUTrack demonstrates that a single model with a unified input representation can effectively handle various common SOT tasks, eliminating the need for task-specific designs and separate training sessions. Additionally, we introduce a task-recognition auxiliary training strategy and a soft token type embedding to further enhance SUTrack's performance with minimal overhead. Experiments show that SUTrack outperforms previous task-specific counterparts across 11 datasets spanning five SOT tasks. Moreover, we provide a range of models catering edge devices as well as high-performance GPUs, striking a good trade-off between speed and accuracy. We hope SUTrack could serve as a strong foundation for further compelling research into unified tracking models. Code and models are available at github.com/chenxin-dlut/SUTrack.